SFUSNet: A Spatial-Frequency domain-based Multi-branch Network for diagnosis of Cervical Lymph Node Lesions in Ultrasound Images

TL;DR

This paper introduces SFUSNet, a novel deep learning model that combines spatial and frequency domain analysis to improve diagnosis accuracy of cervical lymph node lesions in ultrasound images, outperforming existing models.

Contribution

The paper proposes SFUSNet, a multi-branch network utilizing a Conv-FFT Block to model ultrasound images in both spatial and frequency domains, achieving state-of-the-art performance.

Findings

SFUSNet achieves 92.89% accuracy in lesion classification.

It outperforms 12 popular architectures in benchmarking.

The model attains high sensitivity and specificity for lesion detection.

Abstract

Booming deep learning has substantially improved the diagnosis for diverse lesions in ultrasound images, but a conspicuous research gap concerning cervical lymph node lesions still remains. The objective of this work is to diagnose cervical lymph node lesions in ultrasound images by leveraging a deep learning model. To this end, we first collected 3392 cervical ultrasound images containing normal lymph nodes, benign lymph node lesions, malignant primary lymph node lesions, and malignant metastatic lymph node lesions. Given that ultrasound images are generated by the reflection and scattering of sound waves across varied bodily tissues, we proposed the Conv-FFT Block. It integrates convolutional operations with the fast Fourier transform to more astutely model the images. Building upon this foundation, we designed a novel architecture, named SFUSNet. SFUSNet not only discerns variances in ultrasound images from the spatial domain but also adeptly captures micro-structural alterations across various lesions in the frequency domain. To ascertain the potential of SFUSNet, we benchmarked it against 12 popular architectures through five-fold cross-validation. The results show that SFUSNet is the state-of-the-art model and can achieve 92.89% accuracy. Moreover, its average precision, average sensitivity and average specificity for four types of lesions achieve 90.46%, 89.95% and 97.49%, respectively.